Development of Text Classification Methods Based on Deep Learning

Xiaoxi Jiang

2024

Abstract

As the Internet continues to grow, more and more text data are being produced online. Proper classification can be beneficial for mining the valuable information contained in text, so management and classification on text data is quite crucial. Text categorization, or the process of adding labels or tags to text units, is one of the classic issues associated with Natural Language Processing (NLP). In the early stage of the research, some researchers put forward the methods of keyword matching and expert rules for text classification, but the effect is poor due to the limitation of matching rules. Fortunately, deep learning as an emerging technology has attracted a lot of attention from researchers. Deep learning-based text classification has shown better categorization performance in the processing of text data. This paper explores the information of various deep learning models in design and application in detail and introduces the relevant methods to improve the efficiency and accuracy of text classification, and finally summarizes the future research directions of deep learning algorithms in the field of text classification.

Paper Citation

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Development of Text Classification Methods Based on Deep Learning
SN - 978-989-758-690-3
AU - Jiang X.
PY - 2024
SP - 518
EP - 523
DO - 10.5220/0012829500004547
PB - SciTePress

in Harvard Style

Jiang X. (2024). Development of Text Classification Methods Based on Deep Learning. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 518-523. DOI: 10.5220/0012829500004547

in Bibtex Style

@conference{icdse24,
author={Xiaoxi Jiang},
title={Development of Text Classification Methods Based on Deep Learning},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={518-523},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012829500004547},
isbn={978-989-758-690-3},
}